paradox-sifter
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow explicitly requires extracting “the exact limitation statements” from “5-10 papers,” meaning the agent at runtime would ingest outsider-authored free text from externally provided/picked papers into the LLM context (e.g., paper body text/limitations sections).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata